Incorporating prior knowledge of a particular task into the architecture of a learning algorithm can greatly improve generalization performance. We study here a case where we know that the function to be learned is non-decreasing in two of its arguments and convex in one of them. For this purpose we propose a class of functions similar to multi-layer neural networks but (1) that has those properties, (2) is a universal approximator of continuous functions with these and other properties. We apply this new class of functions to the task of modeling the price of call options. Experiments show improvements on regressing the price of call options using the new types of function classes that incorporate the a priori con(cid:173) straints.

About the Author: Alexandre Hubert began his career as a trader in the city of London, and shifted to become a data scientist after four years. He has worked on a wide range of use cases, from creating models that predict fraud to building specific recommendation systems. Alex has also worked on loan delinquency for leasing and refactoring institutions as well as marketing use cases for retailer bankers. Alex is a lead data scientist at Dataiku, located in Singapore.